Don't Learn Prompt Engineering. Here's What Matters More
Source: Dev.to
I originally posted this post on my blog.
I’m not an AI evangelist, and I’m not a hater either.
I’ve tried AI for coding (see my experience). After a week or two I noticed how dependent I was becoming (the problem explained). Since then I’ve used AI only for small coding tasks—generating tiny functions or spotting typos—rather than treating English as my primary programming language.
Marcus Hutchins, a security researcher, puts it boldly in his post Every Reason Why I Hate AI and You Should Too:
“I’d make a strong argument that what you shouldn’t be doing is ‘learning’ to do everything with AI. What you should be doing is learning regular skills. Being a domain expert prompting an LLM badly is going to give you infinitely better results than a layperson with a ‘World’s Best Prompt Engineer’ mug.”
I agree with the core message.
The Argument
When everybody is relying on AI, it’s time to return to old‑school habits:
- Read code
- Write trustworthy tests
- Devour classic textbooks
- Troubleshoot bugs with pen and paper
Outside of coding, the same principles apply: read books on paper, take notes by hand, and write your own summaries to develop taste and judgment.
Using AI is like holding a calculator on a math exam: even the best calculator is useless if you don’t know what to compute. Build solid skills first, then leverage AI.
Old‑School Practices
Coding isn’t just about manipulating symbols—where AI shines—but also about communicating with non‑technical managers, negotiating deadlines, and saying “no” politely. Those interpersonal skills are essential for confidence and effectiveness.
Conclusion
That’s why I wrote Street‑Smart Coding: 30 Ways to Get Better at Coding, to share the skills I wish I’d learned early on.
Get your copy of Street‑Smart Coding here. It’s the roadmap I wish I had when I was starting out.